© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19120
    Prev
    Next
    INDEX
    Explanations

    Safety, risks, and specific items/groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     règ
    0.56
     arbeid
    0.53
    անդ
    0.52
    ют
    0.52
     razon
    0.50
    ewerk
    0.50
    َة
    0.49
    硖
    0.49
    ету
    0.49
    viron
    0.47
    POSITIVE LOGITS
     Alaskan
    0.66
     Alaska
    0.64
    Alaska
    0.64
     आदिवासी
    0.59
     Navajo
    0.57
     Sarawak
    0.54
     Arunachal
    0.54
     Papua
    0.54
     Oklahoma
    0.53
     ಹು
    0.52
    Activations Density 0.011%

    No Known Activations